Everything Search MCP Server

What does “Everything Search” MCP Server do?

The Everything Search MCP Server is a cross-platform Model Context Protocol (MCP) server designed to provide fast and efficient file searching capabilities for AI assistants and developers. By bridging the gap between AI agents and system-level search tools, it enables natural-language-driven file and folder queries across Windows, macOS, and Linux systems. On Windows, it leverages the powerful Everything SDK; on macOS, it utilizes the built-in Spotlight database via mdfind; and on Linux, it integrates with locate or plocate. This allows AI workflows to seamlessly surface file metadata, quickly locate resources, or automate search-driven tasks as part of broader development and automation pipelines. The Everything Search MCP Server enhances productivity by making deep, contextual file search accessible to LLMs and development tools.

List of Prompts

No explicit prompt templates are specified in the repository documentation or files.

List of Resources

No explicit MCP resources are mentioned in the available documentation or repository files.

List of Tools

• search
  Search for files and folders across the system using platform-specific tools. Supports a flexible set of parameters, including:
  • query: Required search query string (platform-specific syntax supported)
  • max_results: Limit on the number of results (default: 100, max: 1000)
  • match_path: Match against full path (default: false)
  • match_case: Case-sensitive search (default: false)
  • match_whole_word: Whole word matching (default: false)
  • match_regex: Regex search (default: false)
  • sort_by: Sorting options (filename, path, size, extension, creation/modification date, etc.)

Use Cases of this MCP Server

• Codebase Exploration:
  Quickly locate source files, scripts, or configuration files in large codebases using advanced search queries and filters.
• System File Auditing:
  Enable AI agents to audit file systems for specific types of content (e.g., logs, executables, or recently modified files) to assist in troubleshooting or compliance checks.
• Automated Documentation Linking:
  Locate project documentation, READMEs, or licenses programmatically and surface them for AI-augmented documentation systems.
• Workflow Automation:
  Integrate fast file search into development workflows to automate repetitive tasks such as finding build artifacts, log files, or temporary assets.
• Data Discovery:
  Allow LLMs to discover data files (e.g., CSVs, datasets, images) relevant to a user’s query for downstream analysis or integration.

How to set it up

Windsurf

1. Ensure you have Python and platform-specific prerequisites installed (see below).
2. Locate and open your Windsurf configuration file.
3. Add the Everything Search MCP Server using a JSON snippet as below.
4. Save the configuration and restart Windsurf.
5. Verify that the MCP server appears in Windsurf and test with a sample search.

Example configuration:

{
  "mcpServers": {
    "everything-search": {
      "command": "python",
      "args": ["-m", "src.mcp_server_everything_search"]
    }
  }
}

Claude

1. Install Python and necessary search utilities for your OS.
2. Open Claude’s configuration/settings panel.
3. Insert the Everything Search MCP Server entry in the MCP section.
4. Save and restart Claude.
5. Use the integrated search tool within Claude to confirm the setup.

Example configuration:

{
  "mcpServers": {
    "everything-search": {
      "command": "python",
      "args": ["-m", "src.mcp_server_everything_search"]
    }
  }
}

Cursor

1. Make sure Python and OS-specific dependencies are installed.
2. Edit Cursor’s user settings or MCP integration file.
3. Add the following MCP server configuration.
4. Save settings and restart Cursor.
5. Confirm by performing a file search within Cursor.

Example configuration:

{
  "mcpServers": {
    "everything-search": {
      "command": "python",
      "args": ["-m", "src.mcp_server_everything_search"]
    }
  }
}

Cline

1. Verify Python and the required system search tools are present.
2. Open Cline’s MCP server configuration.
3. Add the Everything Search MCP Server as shown below.
4. Save and restart Cline.
5. Test the MCP integration by issuing a search command.

Example configuration:

{
  "mcpServers": {
    "everything-search": {
      "command": "python",
      "args": ["-m", "src.mcp_server_everything_search"]
    }
  }
}

Securing API Keys & Environment Variables

To secure sensitive data or API keys, use environment variables in your MCP configuration:

{
  "mcpServers": {
    "everything-search": {
      "command": "python",
      "args": ["-m", "src.mcp_server_everything_search"],
      "env": {
        "SOME_API_KEY": "${SOME_API_KEY}"
      },
      "inputs": {
        "api_key": "${SOME_API_KEY}"
      }
    }
  }
}

Note: Replace "SOME_API_KEY" with the actual environment variable name as required by your setup.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "everything-search": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “everything-search” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available documentation, “Everything Search” MCP Server provides excellent clarity on its purpose and tool functionality, but lacks explicit prompt templates, resources, or advanced MCP features like sampling or roots. Its documentation is clear and it is actively maintained. Overall, it is a solid utility for file search use-cases, but not a comprehensive example of all MCP capabilities.

MCP Score